# Liquid d1 (slim)

> d1 is Liquid AI's decision model family. It answers typed yes or no, choice and score questions about text and images with probabilities, through a hosted API and the open-weight d1-3B and d1-omni-600M models.

- Full: https://www.anchorterminal.com/tools/liquid-d1.md (~7,650 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/liquid-d1.json · canonical https://www.anchorterminal.com/tools/liquid-d1
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-08

**E · 43.5/100 · rank #582 of 629 · #8 in Decision models · not agent-ready · confidence medium**


Assessment: The hosted API costs $0.04 per million input tokens and takes TypeSafe's System One request, and the d1-3B weights run locally through Transformers or llama.cpp. Liquid's terms allow it to train on API content, and no status page, rate limits or error reference were found. The family launched between 22 September and 7 October 2026.

## Facts

- Kind: Model API · vendor: Liquid AI · category: Decision models · legal entity: Liquid AI, Inc. · provenance 62/100
- Endpoint: `https://api.liquid.ai/decisions/v1/systemone` (HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: The hosted d1 model is proprietary under Liquid AI's terms of service. The d1-3B and d1-omni-600M weights and model code are under the LFM Open Licence v1.0, which is based on Apache-2.0 and conditions commercial use on annual revenue under $10 million. Training code and data aren't published
- Probe metrics: not measured yet (probes haven't run)
- Models: Hosted `d1` (text and images) and `d1:free` (text only). Open weights d1-3B (3.12B parameters, from LFM2.5-VL-3B, text and images) and d1-omni-600M (587M, text with images or audio, described as experimental)
- Question types: noul, choice and score (2 to 10 levels), several a request, in the request shape of TypeSafe's System One API
- Input: State as text or JSON, plus up to 8 JPEG, PNG, WebP or GIF images as Base64 on the hosted `d1`. JSON body under 4.5 MB and at most 10,000 image patches a request
- Context: 32,768 tokens for d1-3B and 16K for d1-omni-600M per Liquid's docs. OpenRouter and Vercel list 65,536 for the hosted d1. Liquid's own docs give no figure for the hosted model
- Free tier: `d1:free`, text only. No limits published
- Trains on API data: Yes. The terms of 30 September 2026 allow training and fine-tuning on submitted content and outputs
- Rate limits: Not found in the reviewed documentation
- Weights: LFM Open Licence v1.0 on Hugging Face, ungated, loaded with `trust_remote_code=True` on transformers 5.14 or later. GGUF builds for llama.cpp, whose server answers `/v1/systemone`
- Licence: Commercial use of the weights is free below $10 million in annual revenue. Above it a paid licence from Liquid is needed. Qualified non-profits are exempt for research and non-commercial use
- Gateways: OpenRouter (`liquid/d1`) and Vercel AI Gateway, each at $0.04 per million input tokens
- Prices: d1 input $0.04 per 1M tokens

- Scores: Reliability 21, Performance pending, Schema & documentation 59, Agent ergonomics 63, Security & auth 35, Payments & pricing 27, Task success pending, Maintenance & community 60, Transparency & trust 54 · total over the 7 assessed categories
- Why: Reliability, Scored as a hosted model API, the surface an outside agent would call, with the open weights noted. · Schema & documentation, No OpenAPI file found. · Agent ergonomics, Read as an API an agent calls for a decision, as with Jev and Clef. · Security & auth, Read for a model API. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read for a model. · Transparency & trust, The hosted model is closed under clear terms.
- Sources: 26, open questions: 14, both in the full twin
- Capabilities: inference.decision
- JSON: https://www.anchorterminal.com/api/v1/tools/liquid-d1.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/liquid-d1.svg` or a link to https://www.anchorterminal.com/tools/liquid-d1 from a page on liquid.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. POST to https://api.liquid.ai/decisions/v1/systemone with a `liquid_` key as a Bearer header. This is not a chat-completions endpoint
2. Use `d1` for images. `d1:free` is text-only and answers that it does not accept images
3. Send images as Base64 data URLs in `images`, at most 8, with the whole JSON body under 4.5 MB. Remote image URLs are refused
4. Budget tokens per question. Each question is billed as its own prompt, with its text and every image counted again
5. Don't send confidential content to the hosted API, since the terms allow training on it. Run d1-3B locally for that data

## Connect

```bash
pip install typesafe-sdk   # or: npm install @typesafe-ai/sdk
```

```bash
curl -s https://api.liquid.ai/decisions/v1/systemone \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"d1","state":"I have been waiting over three weeks for my order and nobody has responded to my emails.","questions":{"is_complaint":{"type":"noul","instructions":"Is this message a complaint from the customer?"}}}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI Decisions API | BB | 71.5 | inference.decision | https://www.anchorterminal.com/tools/openai-decisions-api.min.md |
| Laya | B | 69.2 | inference.decision | https://www.anchorterminal.com/tools/convai-laya.min.md |
| Kev | B | 67.4 | inference.decision | https://www.anchorterminal.com/tools/jaredpalmer-kev.min.md |
| Vela 2.0 | B | 66.5 | inference.decision | https://www.anchorterminal.com/tools/vela.min.md |
| Clef | B | 66.1 | inference.decision | https://www.anchorterminal.com/tools/cloudflare-clef.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)